Visual speed adaptation for improved sensor coverage in a multi-vehicle survey mission

Autonomous underwater vehicles (AUVs) often perform high-resolution survey missions. Such missions are often planned on low resolution bathymetry maps using offline coverage planning methods, e.g., using a standard lawn-mower trajectory that is adapted to the coarse-resolution representation of the terrain. We present in this paper an approach to adapt the exploration online during the mission, namely by adapting the vehicle speed as a crucial parameter with which the planned survey path is tracked. The main idea is to determine online during the mission whether the currently surveyed environment part is interesting or not and to accordingly change the speed, i.e., to move slower over interesting and faster over less interesting terrain. Concretely, this paper proposes two alternative methods to compute terrain complexity metrics that can be used for adjusting the speed of a single vehicle or a formation of vehicles online during the mission. The first methods computes the anisotropy of camera images using the local radius index (LRI) to assess 2D texture complexity. The second method fits planar patches into stereo data to estimate the 3D ruggedness of the terrain. The effectiveness of the methods is shown using visual stereo survey data. A description of field trials where the methods were used to control the speed of a multi-vehicle formation during a complex survey mission further exemplifies the usefulness of the methods.